De-RPOTA: Decentralized Learning With Resource Adaptation and Privacy Preservation Through Over-the-Air Computation
IEEE/ACM Transactions on Networking · 2024-12 · 32 (6) · 4931-4943
DOI: 10.1109/tnet.2024.3438462 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE/ACM Transactions on Networking, 2024-12. Verfasst von Jing Qiao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: National Science Fund for Excellent Young Scholars of China, Major Basic Research Program of Shandong Provincial Natural Science Foundation, National Natural Science Foundation of China.
Abstract (Originalsprache)
In this paper, we propose De-RPOTA, a novel algorithm designed for decentralized learning, equipped with mechanisms for resource adaptation and privacy protection through over-the-air computation. We theoretically analyze the combined effects of limited resources and lossy communication on decentralized learning, showing it converges towards a contraction region defined by a scaled errors version. Remarkably, De-RPOTA achieves a convergence rate of $\mathcal {O}\left ({{\frac {1}{\sqrt {nT}}}}\right)$ in scenarios devoid of errors, matching the state-of-the-arts. Additionally, we tackle a power control challenge, breaking it down into transmitter and receiver sub-problems to hasten the De-RPOTA algorithm’s convergence. We also offer a quantifiable privacy assurance for our over-the-air computation methodology. Intriguingly, our findings suggest that network noise can actually strengthen the privacy of aggregated information, with over-the-air computation providing extra security for individual updates. Comprehensive experimental validation confirms De-RPOTA’s efficacy in communication resources limited environments. Specifically, the results on the CIFAR-10 dataset reveal nearly 30% reduction in communication costs compared to the state-of-the-arts, all while maintaining similar levels of learning accuracy, even under resource restrictions.
Förderung
- National Science Fund for Excellent Young Scholars of China
- Major Basic Research Program of Shandong Provincial Natural Science Foundation
- National Natural Science Foundation of China
- Shandong Provincial Natural Science Foundation of China
Zitieren
APA
Qiao, J., Shen, S., Chen, S., Zhang, X., Lan, T., Cheng, X., & Yu, D. (2024). De-RPOTA: Decentralized Learning With Resource Adaptation and Privacy Preservation Through Over-the-Air Computation. IEEE/ACM Transactions on Networking, 32(6), 4931-4943. https://doi.org/10.1109/tnet.2024.3438462
Vancouver
Qiao J, Shen S, Chen S, Zhang X, Lan T, Cheng X, et al. De-RPOTA: Decentralized Learning With Resource Adaptation and Privacy Preservation Through Over-the-Air Computation. IEEE/ACM Transactions on Networking. 2024;32(6):4931-4943. doi:10.1109/tnet.2024.3438462
BibTeX
@article{Qiao2024,
author = {Qiao, Jing and Shen, Shikun and Chen, Shuzhen and Zhang, Xiao and Lan, Tian and Cheng, Xiuzhen and Yu, Dongxiao},
title = {De-RPOTA: Decentralized Learning With Resource Adaptation and Privacy Preservation Through Over-the-Air Computation},
journal = {IEEE/ACM Transactions on Networking},
year = {2024},
volume = {32},
number = {6},
pages = {4931--4943},
doi = {10.1109/tnet.2024.3438462}
}
EUVIMED